Be the first to get access to new connectors. Get early access →
ConnectorBay Early access
Discover
VoiceCmd icon

VoiceCmd

A brand-neutral voice-assistant command reference, a real command checker, and troubleshooting tips

Unify Dynamics LLC

Documentation
Tools7read-only
Sign-inNoneno account, no key
Data keptNoneprocessed in memory
PriceFreeoptional Pro limits
StatusLiveMCP + REST
Works withMCP · RESTany agent

Try asking

Real questions, and the tools your agent calls to answer them.

What's a good way to phrase a reminder command?
Tools called
category_detail
What kinds of voice commands are there?
Tools called
command_categories
Is 'turn off' a complete smart-home command?
Tools called
classify_command
Why might 'call' on its own fail?
Tools called
classify_command
Why didn't it understand what I said?
Tools called
voice_troubleshoot
Give me a full voice-assistant troubleshooting checklist
Tools called
voice_troubleshoot_list
What does wake word mean?
Tools called
voice_glossary
Search for anything about volume commands
Tools called
search

About

VoiceCmd is a fully local, brand-neutral voice-assistant command reference. command_categories lists every command category this reference covers — timers/alarms/reminders, smart-home control, information queries, media control, calls & messaging, lists & shopping, routines/scenes, and navigation & traffic; category_detail gives one category's full phrasing patterns, example utterances, and tips. classify_command scores a raw command string against every category by keyword overlap and genuinely checks for the specific detail that category needs — a duration/time, a device/room, a recipient, an item, a destination — flagging it as likely to fail when it's missing. voice_troubleshoot matches a symptom description to likely causes and fixes; voice_troubleshoot_list gives the full troubleshooting reference. voice_glossary defines terms like wake word, utterance, intent, slot/entity, far-field microphone and barge-in. search does free-text keyword search across all of it. Brand-neutral: describes patterns shared across assistant platforms, never one product's proprietary syntax. Keyless; fully local; zero upstream calls; nothing stored.

Sources: Computed locally / hand-curated — general voice-assistant command patterns, categories and troubleshooting causes/fixes drawn from common, brand-neutral practice across smart-speaker platforms; fully local, zero upstream calls

Privacy

The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.

Data not collectedNo account, no profile, no stored prompts or results.
Privacy policyTerms

What it can do

7 tools, grouped by job. Every one is read-only or compute-only.

OpenAPI
Categories2 tools
  • Command categoriesEvery voice-command category this reference covers, with a short description and its trigger keywords — timers/alarms/reminders, smart-home…
  • Category detailFull detail for one command category: general phrasing patterns, example utterances, and practical tips for getting it recognized reliably.
Command Checker1 tools
  • Classify commandClassify a raw command string into its most likely category and check whether it actually includes the specific detail that category needs to…
Troubleshooting2 tools
  • Voice troubleshootMatch a symptom description to the closest known failure mode and return its likely causes and concrete fixes — ambient noise, ambiguous phrasing,…
  • Voice troubleshoot listThe full troubleshooting reference: every known voice-command failure mode with its causes and fixes.
Reference2 tools
  • Voice glossaryDefinitions of common voice-assistant terms — wake word, utterance, intent, slot/entity, far-field microphone, skill/routine, multi-turn…
  • SearchFree-text keyword search across command categories, the troubleshooting reference, and the glossary at once.

Information

PublisherUnify Dynamics LLC
CategoryHome & lifestyle
LanguagesEnglish
Built forGlobal (brand-neutral, general patterns)
CompatibilityAny MCP client · any agent · REST
Version0.1.0
MCP endpointhttps://voicecmd.connectorbay.com/mcp
REST APIopenapi.json
SupportGet help · Status
CountryWorldwide

More like this

CloudCompare

Brand-neutral storage-plan sizing: inventory math, growth projection, and media size estimates

Live · MCP + REST3 tools

PDFHandy

PDF task how-to reference, a PDF/A explainer, and a why-is-my-PDF-so-large diagnostic

Live · MCP + REST3 tools

Govee (BYOK)

Read your Govee devices and their state and change lights and plugs (power, brightness, color, color temperature) with your own Govee API key

Live · MCP + REST8 tools

Wattwatchers (BYOK)

Read your Wattwatchers energy monitors: device status, channel setup, 30-second and 5-minute energy, voltage and current readings with your own API key

Live · MCP + REST9 tools

UK Energy Performance Certificates (BYOK)

Search and read England and Wales energy performance certificates (EPC, non-domestic and display) with your own bearer token

Live · MCP + REST7 tools

ShowMojo (BYOK)

Read your ShowMojo rental listings, properties and tour availability with your own account API token

Live · MCP + REST6 tools

Documentation

Back to top

What VoiceCmd is for

A brand-neutral reference for how voice-assistant commands are generally phrased, why a command might fail, and a real checker for whether a specific command has the detail it needs to succeed.

What it does

VoiceCmd is a fully local, hand-curated, brand-neutral voice-assistant command reference. command_categories lists every command category — timers/alarms/reminders, smart-home control, information queries, media control, calls & messaging, lists & shopping, routines/scenes, and navigation & traffic; category_detail gives one category's full phrasing patterns, example utterances, and tips. classify_command scores a raw command string against every category by keyword overlap and genuinely checks whether the specific detail that category needs — a duration/time for a timer, a device/room for smart-home control, a recipient for a call or message, an item for a list, a destination for navigation — is actually present, flagging it as likely to fail when it's missing rather than only guessing a category. voice_troubleshoot matches a symptom description ("it didn't understand me", "the wrong speaker responded") to likely causes and fixes; voice_troubleshoot_list gives the full reference. voice_glossary defines terms like wake word, utterance, intent, slot/entity, far-field microphone, and barge-in. search does free-text keyword search across categories, troubleshooting, and the glossary at once. Keyless; fully local; zero upstream calls; nothing stored.

What it is not

Not tied to, affiliated with, or endorsed by any specific voice-assistant product — every category, pattern, and troubleshooting entry describes behavior common across many smart-speaker platforms in general terms, never one product's exact wake-word, proprietary syntax, or skill catalog. Not a live command executor: VoiceCmd never sends a command anywhere or controls any device. classify_command's "likely to succeed" result is a structural check (is the needed information present in the text), not a guarantee any real assistant will accept the exact phrasing. Fully local, zero upstream calls, nothing stored.

Privacy policy

Back to top

VoiceCmd — Privacy Policy

Effective 28 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What VoiceCmd is. VoiceCmd is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for a brand-neutral voice-assistant command reference — command phrasing patterns, a command classifier, troubleshooting tips, and a glossary of voice-assistant terms. You interact with your assistant; the assistant sends us only the arguments needed for that one lookup or check.

What we receive. The arguments of each tool call — things like a raw command string you want classified, a symptom description, a category name, or a glossary term — the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.

Everything is answered from bundled reference data or computed on the fly, and nothing is stored. No request is forwarded to any third party — there is no upstream call at all — and no query is logged in request bodies, recorded, or used to train anything.

What we do not receive or store. We do not receive your conversation with the assistant, your name, or any actual voice recording — VoiceCmd only ever sees the text you or your assistant sends it as tool arguments. We do not build a profile from your queries: each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.

Sub-processors. None — all reference data is bundled with the server and every calculation runs locally. Hosting: Vercel (United States regions).

Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.

Children. VoiceCmd is a general-audience service operated by the adult using the assistant.

Changes. We will post changes here with a new effective date.

Terms of service

Back to top

VoiceCmd — Terms of Service

Effective 28 September 2026. These terms govern use of the VoiceCmd connector ("the Service") operated by Unify Dynamics LLC ("we", "us").

  1. The Service. VoiceCmd returns a brand-neutral voice-assistant command reference: command categories with phrasing patterns and examples, a command classifier, a troubleshooting reference, and a glossary of voice-assistant terms. It is accessed through an AI assistant or directly over MCP or HTTP.
  2. Brand-neutral, informational only. VoiceCmd is an independent reference, not affiliated with, endorsed by, or representing any specific voice-assistant product or manufacturer. It describes command patterns and behavior common across the category of smart-speaker and voice-assistant platforms in general terms, not any single product's proprietary wake-word, exact syntax, or skill catalog.
  3. Not a command executor. VoiceCmd never sends a command to, or controls, any actual device, account, or service. classify_command's "likely to succeed" result is a structural text check, not a guarantee that any real assistant will accept the exact phrasing.
  4. Content varies. Real voice-assistant behavior varies by platform, region, language, and software version; this reference describes general, commonly observed patterns, not a specification of any one product.
  5. Acceptable use. Automated use within the published rate limits is welcome.
  6. Availability. The Service is provided "as is" without warranty. We may change, limit or discontinue it at any time.
  7. Data. Our Privacy Policy describes what we process. In short: your query is answered from bundled reference data or a local computation, and nothing is stored.
  8. Pro keys. Optional Pro API keys are issued at our discretion, are personal to the holder and may be revoked for abuse.
  9. Liability. To the fullest extent permitted by law, Unify Dynamics LLC is not liable for any loss arising from use of or reliance on the Service. Our total liability is limited to US $100.
  10. Governing law. California law; venue in San Mateo County, California.
  11. Contact. Unify Dynamics LLC · agent@connectorbay.com · https://connectorbay.com/voicecmd

Support

Back to top

VoiceCmd support

Email agent@connectorbay.com. We answer within two business days.

When you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. VoiceCmd never asks for them.

Get VoiceCmd

Free · No sign-in · Read-only

Streamable HTTP, stateless, no authentication. Paste the endpoint into any MCP-capable agent.

https://voicecmd.connectorbay.com/mcp
{
  "mcpServers": {
    "voicecmd": {
      "type": "http",
      "url": "https://voicecmd.connectorbay.com/mcp"
    }
  }
}